Data Analytics Machine Learning

Yijing Luo

+1-786-***-**** *******@**.*** Cupertino, CA LinkedIn

EDUCATION

Boston University Boston, MA

M.S. in Applied Business Analytics Sept. 2023 - Aug. 2024 The University of Miami Miami, FL

B.S. in Mathematics, Minor in Psychology Sept. 2018 - Jun. 2022 SKILLS

Programing: Python (NumPy, Pandas), SQL, R Studio, Excel (Pivot Tables, VLOOKUP), SQLite Analytics: Exploratory Data Analysis (EDA), A/B Testing, Hypothesis Testing, Regression, Clustering, Time Series, Decision Trees Tools: QuickBooks, Sage 100, Tableau, Power BI, Matplotlib, Salesforce Certificates: Google Analytics, IBM Data Analytics (Intro, Excel, Visualization) PROFESSIONAL EXPERIENCE

H&R Block San Jose, CA

Accounting & Data Analytics Specialist April. 2025 - Current

• Developed financial dashboards using Excel (Pivot Tables, VLOOKUP) to track utility costs, identifying trends that reduced expenses by 15%.

• Improved AP workflow accuracy by reconciling vendor discrepancies and optimizing financial records using Sage 100 and QuickBooks.

• Collaborated cross-functionally to validate and clean financial data, preparing datasets for reporting and identifying anomalies.

• Built reports to summarize operational trends, providing actionable insights to management. Quantumera AI Boston, MA

Data Scientist Intern Jun. 2024 - Aug. 2024

• Designed and optimized SQL queries for transportation datasets, reducing query latency by 15% and improving storage efficiency.

• Performed in-depth analysis on large transportation datasets using Python (Pandas, NumPy), addressing missing values, outliers, and inconsistencies, which improved model performance and forecast accuracy by 20%.

• Applied machine learning algorithms to forecast peak congestion periods and optimize traffic flow, resulting in a 10% decrease in commute delays.

• Designed and implemented interactive Tableau dashboards tracking KPIs and delivering actionable insights, replacing manual reports and enabling real-time decision-making for client stakeholders. HUAXI Securities Co., Ltd Dongguan, China

Data Analyst Intern Nov. 2022 - Jan. 2023

• Optimized 15+ complex SQL queries by analyzing execution plans and improving indexing strategies, reducing average runtime by 30% and accelerating team-wide data processing for client projects.

• Designed and executed A/B tests for a corporate website redesign, utilizing Google Analytics to track user behavior and measure engagement, resulting in a 12% uplift in conversion rates.

• Presented A/B test findings to key stakeholders, leading to the adoption of the highest-performing design and the integration of data-driven analytics best practices across the company.

PROJECT EXPERIENCE

Machine Learning for Lead Conversion Prediction Sept. 2024 - Nov. 2024

• Built a logistic regression model using Python to predict lead conversions, achieving 85% accuracy and 0.82 AUC.

• Developed and fine-tuned a Random Forest model with SMOTE oversampling, achieving 88% accuracy and 0.89 AUC, and improving minority class recall by 30%.

• Identified high-impact predictors (mobile visits, repeat visits), providing actionable insights for lead prioritization and resource allocation.

• Increased F1-score for converted leads from 0.45 to 0.65 by addressing class imbalance and incorporating cost-sensitive metrics.

• Visualized model findings to support data-driven marketing strategies. Airbnb Price Prediction and Customer Segmentation Jan. 2024 - Mar. 2024

• Cleaned and transformed 10K+ Airbnb listings for modeling by handling missing data, encoding variables, and normalizing prices.

• Built multiple linear regression (R = 0.586) to predict prices using key features, guiding hosts on revenue optimization.

• Improved model clarity via multicollinearity checks (VIF, correlation matrix) and feature pruning.

• Predicted listing attributes with classification models (Naive Bayes, KNN, Decision Tree), achieving 94.6% accuracy on rating predictions.

• Applied K-means clustering to segment pricing tiers, supporting differentiated pricing strategies. Production Efficiency Optimization for Amazon Jun. 2023 - Aug. 2023

• Analyzed 2,000+ machine packaging output samples using R, applying hypothesis testing and 95% confidence interval analysis to assess operational efficiency improvements.

• Optimized robotic arm speed settings through iterative statistical modeling, increasing packaging throughput by 40+ units/hour (12% gain).

• Designed operational dashboards in Tableau to monitor real-time production metrics, presenting data-driven recommendation, directly leading to pilot implementation of speed optimization strategy across 3 packaging lines.

Contact this candidate